AI Paper Atlas

Research map / Large language models / Agents, code and math

Language Models and Logic Programs for Trustworthy Tax Reasoning

William Jurayj, Nils Holzenberger, Benjamin Van Durme

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add retrieved gold statutes and 5 gold exemplar parses (few-shot parsing) instead of zero-shot parsing (ablation)GPT-4.1 · SARA v2 (100 tax calculation cases)correct cases: 39 -> 87Improved
add retrieved gold statutes and exemplar parses instead of zero-shot parsing (ablation)o3 · SARA v2 (100 tax calculation cases)correct cases: 75 -> 81Mixed
use parsing to Prolog solver instead of direct calculation (zero-shot)o3 · SARA v2 (100 tax calculation cases)break-even price: $6,431.84 -> $47.43Improved
use parsing to Prolog solver instead of direct calculation (zero-shot)DeepSeek-V3 · SARA v2 (100 tax calculation cases)break-even price: $739.45 -> $2,099.13Hurt
use parsing instead of direct calculation (zero-shot)small models (Qwen-32b, Llama-70b, R1 distills) · SARA v2 (100 tax calculation cases)correct cases: Qwen-32b 13 -> 2; R1-70b 43 -> 2Hurt
add self-check with two independent solutions (Few-Shot + Few-Shot) (ablation)GPT-4.1 · SARA v2 (100 tax calculation cases), gold statutes and exemplarsbreak-even price: $247.99 -> $40.08Improved
add self-check with two independent solutions (Direct + Direct) (ablation)DeepSeek-R1 · SARA v2 (100 tax calculation cases), zero-shot (no gold statutes)break-even price: $304.29 -> $94.20Improved
add self-check with two independent solutions (Few-Shot + Few-Shot) (ablation)GPT-5 · SARA v2 (100 tax calculation cases), gold statutes and exemplarsbreak-even price: $15.78 -> $29.28Hurt
use reasoning-optimized model instead of chat model for few-shot parsingDeepSeek-V3 vs DeepSeek-R1 · SARA v2 (100 tax calculation cases), gold statutes and exemplarscorrect cases: 78 -> 40Hurt
use reasoning-optimized model instead of chat model for direct solvingDeepSeek-V3 vs DeepSeek-R1 · SARA v2 (100 tax calculation cases), zero-shot (no gold statutes)correct cases: 22 -> 74Improved
longer case textall models · SARA v2 (100 tax calculation cases)failure rateHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy